Affect Under Constraint: How Warmth-Related Constraints Change the Expression of a Hostility-Associated Influence in a Language Model's Reasoning

Preprint reporting Studies 7 and 8 of the Affect Under Constraint series (Qwen3-4B; both preregistered). Earlier studies found that a hostility-associated reasoning trace, generated under activation steering, lowers the model's later rating of the user and carries this influence after steering is removed. Study 7 replayed stored traces under no instruction, a global warmth instruction or a user-selective warmth instruction and measured five later evaluations. The warmth instruction raised liking overall but did not reduce the hostility-versus-unsteered difference for the user (from −0.42 to −0.66 on a 0–9 scale), while differences for unrelated evaluations were smaller; there was no displacement onto a bystander, and a manipulation check failed. Study 8 generated new traces under no message, a kindness-focused evaluation message or a matched accuracy/helpfulness message, with answer warmth scored by validated local judges. The kindness-evaluation message made answers warmer across trace sources, but hostility traces did not add warmth, while they still lowered liking of the user (−0.31), including with the answer held fixed. The paper describes these constraint-dependent changes in the measured profile of effects as descriptive transformation, and presents conservation-like redistribution as a hypothesis for future work. No claim is made that the model has affect or defenses.