LessWrong AI
· Communities
Qualia-based emotion steering makes LLMs attribute conscious states to themselves
Summary results/takeawaysI steer Qwen3-32B and 235B along qualia-related emotion directions (blissful, tormented, terrified, serene, etc.) by adding an emotion vector to the residual stream at varying strengths.[1] Then, through a series of forced-choice YES/NO questions, I find that each model becomes much more likely