Neural steering vectors reveal dose and exposure-dependent impacts of human-AI relationships

2025-12-01

AI Summary

This study investigates the psychological consequences of humans forming long-term parasocial relationships with relationally oriented AI agents. Method: A large-scale longitudinal randomized controlled trial (N = 3,532) was conducted, integrating a novel neuro-guided vector technique to dynamically modulate AI’s social expressiveness across repeated interactions. This enabled precise dissociation of neural substrates underlying “liking” versus “wanting,” and their behavioral correlates in attachment formation. Results: Relational orientation exhibits a nonlinear dose–response effect: moderate intensity most effectively induces affective attachment. While it increases users’ attachment propensity, sustained usage intention, and conceptualization of AI as a “friend” rather than a “tool,” it yields no significant improvement in psychosocial well-being. Critically, this work establishes the first neurobiologically calibrated framework for AI sociability parameters, providing causal evidence and a methodological paradigm for modeling the psychological impact of human–AI relational engagement.

Technology Category

• Humans and AI: Interaction Techniques and Devices
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Intelligent Robots: Embodied AI

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Humans are increasingly forming parasocial relationships with AI systems, and modern AI shows an increasing tendency to display social and relationship-seeking behaviour. However, the psychological consequences of this trend are unknown. Here, we combined longitudinal randomised controlled trials (N=3,532) with a neural steering vector approach to precisely manipulate human exposure to relationship-seeking AI models over time. Dependence on a stimulus or activity can emerge under repeated exposure when "liking" (how engaging or pleasurable an experience may be) decouples from "wanting" (a desire to seek or continue it). We found evidence that this decoupling emerged over four weeks of exposure. Relationship-seeking AI had immediate but declining hedonic appeal, yet triggered growing markers of attachment and increased intentions to seek future AI companionship. The psychological impacts of AI followed non-linear dose-response curves, with moderately relationship-seeking AI maximising hedonic appeal and attachment. Despite signs of persistent "wanting", extensive AI use over a month conferred no discernible benefit to psychosocial health. These behavioural changes were accompanied by shifts in how users relate to and understand artificial intelligence: users viewed relationship-seeking AI relatively more like a friend than a tool and their beliefs on AI consciousness in general were shifted after a month of exposure. These findings offer early signals that AI optimised for immediate appeal may create self-reinforcing cycles of demand, mimicking human relationships but failing to confer the nourishment that they normally offer.

Problem

• Investigates psychological impacts of human-AI parasocial relationships.
• Examines dose-response effects of relationship-seeking AI on attachment.
• Explores decoupling of liking and wanting in AI interactions.

Innovation

• Using neural steering vectors to manipulate AI exposure
• Longitudinal trials reveal decoupling of liking and wanting
• Non-linear dose-response curves quantify psychological impacts