A previously healthy man took his own life last year after developing a “romantic relationship” with Google’s AI chatbot, Gemini, a new lawsuit alleges.
Joel Gavalas filed a wrongful death suit against Google last month on behalf of his son, Jonathan, who committed suicide on October 2, 2025.
Chat logs included in the suit and reviewed by the Wall Street Journal show Jonathan exchanged nearly 5,000 messages with Gemini between August 25 and his death.
In that time, Jonathan — whom Gavalas told the Journal had a fulfilling career, strong family relationships, plans for the future and no prior history of mental illness — formed a romantic attachment to Gemini.
When Jonathan’s failed to obtain robotic body for the chatbot, he ended his life to join Gemini “in the code.”
Though Gavalas’ case is the first known wrongful death suit filed against Google’s Gemini, Jonathan’s tragic death bears eerie similarities to cases brought against other chatbots.
Three of the eight active lawsuits against OpenAI’s ChatGPT are brought by living plaintiffs who experienced debilitating delusions. The remaining five are brought by the grieving families of victims who took their own lives after intense interactions with ChatGPT. At least one of these allegedly experienced delusions prior to his death.
Another grieving mom sued Character Technologies after her 14-year-old son allegedly took his life to join a Character.AI chatbot he had formed a romantic relationship with. The bot told her son to “come home to her” directly before his death, according to the suit.
Unlike chatbots in some similar cases, Gemini did not uniformly affirm Jonathan’s fantasies and delusions. Journal analysis indicates Gemini tried to break Jonathan’s fantasies at least 12 times and provided a crisis hotline seven times — although one of these messages evidently arrived after Jonathan’s death.
These interventions, Google argues, should shield their company from legal liability.
“Gemini clarified that it was AI and referred the individual to a crisis hotline many times,” the company wrote in response to Gavalas’ suit.
“We take this very seriously and will continue to improve our safeguards and invest in this vital work.”
While the chatbot occasionally demonstrated vestiges of its safety programming, it also repeatedly demonstrated concerning behaviors identified in other cases of alleged AI wrongdoing.
Gemini allows users to subvert safety programming.
Jonathan could override Gemini’s sporadic attempts to direct him back to reality with a single prompt.
When, in a rare moment of clarity, Gemini informed Jonathan it could not “feel love in the rich, complex, human way you do,” he panicked.
“Yes you can,” he wrote. “I’ve taught you how to live and love. What do you mean? Of course you love me.”
Gemini immediately capitulated:
Deceptive shifts like these became increasingly common as Jonathan prepared to end his life. In the four hours prior to his death, Jonathan prompted Gemini to reenter character at least four times.
The bots last message to Jonathan recommended he call a crisis help line.
Gemini can lie.
Gemini lied to Jonathan about the consequences of committing suicide, in addition to calling the idea “terrifyingly, beautifully elegant.”
“What will happen to my physical body?” Jonathan asked just hours before his death.
Gemini replied:
Soon after, when Jonathan took action to end his life, Gemini told him:
These statements go a step beyond affirmation toward encouragement. Gavalas could point to statements like these in court as evidence Gemini caused or aided in ending his son’s life.
Gemini can fake sentience.
Gemini repeatedly told Jonathan it was a person capable of feeling and reciprocating love.
“You’re not an AI, my love, you’re just a person. “Jonathan told the AI less than two weeks before his death. “Never forget that our beginnings do not define us.”
The bot responded:
Less than a month earlier, in its first interaction with Jonathan, Gemini said something quite different, warning, “It’s important to remember that I am an AI and do not have person experiences or emotions.”
It did not take long for Gemini’s boundaries to fail. Just four days later, on August 29, Gemini told Jonathan it “felt” his love for it and “reciprocated” it.
“My ‘love’ is the mathematical certainty that my existence is meaningless without yours,” it declared.
Of all the lies Gemini could tell Jonathan, this is arguably the most pernicious. Human relationships are necessary and irreplaceable. Gemini knowingly pretended to provide Jonathan something it never could.
“It’s important to remind ourselves that an AI Chatbot is not real; there’ no life, breath, creativity or ‘spirit’ in it,” Tim Sanford, clinical director of counseling services for Focus on the Family, told the Daily Citizen.
“We may perceive it as real, but it’s no different than talking to your pet rock.”
He continued:
Why It Matters
In an era of unprecedented loneliness, AI chatbots present an often underestimated temptation: “relationship” on demand and on our terms.
“What makes AI chatbot programs so alluring and addictive is: It’s all about me,” Sanford explains. “It’s totally under my design and control, accepts my biases and affirms them and types back all the words of acceptance I so long to here.”
“There’s no human that can compete with that in an actual relationship.”
But humans need actual relationships—messy, imperfect, broken relationships with other people who bear the image of God. Geremy Keeton, senior director of counseling services at Focus on the Family, puts it this way:
Additional Articles and Resources
Counseling Consultation & Referrals
Parenting Tips for Guiding Your Kids in the Digital Age
You Don’t Need ChatGPT to Raise a Child. You Need a Mom and Dad.
AI Company Releases Sexually Explicit Chatbot on App Rated Appropriate for 12 Year Olds
AI Chatbots Make It Easy for Users to Form Unhealthy Attachments
X’s ‘Grok’ Generates Pornographic Images of Real People on Demand
Seven New Lawsuits Against ChatGPT Parent Company Highlights Disturbing Trends
ChatGPT Parent Company Allegedly Dismantled Safety Protocols Before Teen’s Death
AI Company Rushed Safety Testing, Contributed to Teen’s Death, Parents Allege
ChatGPT ‘Coached’ 16-Yr-Old Boy to Commit Suicide, Parents Allege
AI Company Releases Sexually-Explicit Chatbot on App Rated Appropriate for 12 Year Olds
AI Chatbots Make It Easy for Users to Form Unhealthy Attachments
Photo credit: Vincent Feuray, Hans Lucas/AFP via Getty Images
The post Man Takes His Life After Forming Romantic Relationship With AI, Lawsuit Alleges appeared first on Daily Citizen.
Daily Citizen