Steering Follows Geometry, Not Labels: Emotion Directions in a Full-Duplex Speech Model

The paper investigates emotion steering in Moshi, a fully open‑source full‑duplex speech language model, across four emotions. Using mean‑difference activation steering—just a few vector additions per frame and no retraining—the authors find that emotion can be linearly decoded from Moshi’s residual stream, but steering is only partially achievable and uneven: happy, angry and surprise steer toward a shared direction while sad is distinctly steerable. They also demonstrate that the shared component across the three emotions cannot simply be projected away from all emotions equally.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• llms
• agents