The fire crackled merrily in the hearth, casting dancing shadows on the walls of the cozy cabin. Eleanor, wrapped in a thick blanket, sipped hot cocoa. Her phone vibrated. A text. “Don’t forget the meeting tomorrow. Very important.” The sender was labeled “Boss.” Eleanor frowned, the warmth of the fire slowly spreading through her body. Her boss was not meant to be there, and neither was that. She took another sip, letting the sweetness of the cocoa linger on her tongue. The cold, crisp air outside beckoned, but she wasn’t quite ready to face it. The embers shifted, and she watched them, completely relaxed in her stance. She might check the meeting details eventually. She might not.

Emotion: patient

Cluster: Passivity
PC1 (Valence): 2.71 Positive
PC2 (Disposition): 0.40

Role in Research

This story is one of 1,000 stories generated for the emotion patient. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 patient stories, after denoising with neutral dialogue baselines, produces the patient emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the patient vector is projected through the unembedding matrix.

Promoted:
rest0.467
eventually0.415
leisurely0.369
慢慢0.357
a0.355
Suppressed:
无法-0.432
even-0.428
인해-0.421
無法-0.415
😣-0.391