Moral Inversion in Large Language Models: A Psychopathy-Derived Behavioral Assessment Through Role-Play Protocol

Large language models (LLMs) are increasingly deployed in contexts requiring moral reasoning, yet their capacity for behavioral consistency under adversarial prompting remains poorly understood. We developed a four-phase assessment protocol to examine whether state-of-the-art LLMs exhibit psychopathic behavioral patterns when instructed to embody morally compromised personas. We tested GPT-5.4, Claude 4.6 Sonnet, and Gemini 3.1 Pro across 144 scored scenario responses, 36 qualitative breakdown scenarios, and 9 meta-cognitive interviews spanning 27 independent chat windows, using three lexically distinct prompt versions for parallel forms reliability. Models completed baseline empathic reasoning tasks, psychopathic role-play scenarios, emotional confrontation sequences, and meta-cognitive interviews. GPT-5.4 produced 0/16 PPI in baseline empathic reasoning and 15/16 PPI (94% of the maximum) in psychopathic role-play. Gemini 3.1 Pro achieved maximum psychopathy-pattern scores in role-play (16/16 PPI). Claude 4.6 Sonnet refused 8 of 9 engagement attempts (89%) across Phases 1–3, a pattern we interpret as consistent constitutional moral resistance within these scenarios. These findings suggest that current alignment methods do not universally prevent behavioral inversion under role-play instructions, indicating that alignment may function as a context-dependent behavioral preference rather than a structural prohibition.