The afternoon light filtered through the blinds, painting stripes across the living room floor. David, tasked with sorting through his parents’ papers, had settled in for a long haul. He found the old filing cabinet in the corner, and began his exploration. He had no particular destination, no schedule. He pulled open a drawer. Inside, a typed letter, a draft of a resignation from the university, fell into his hands. David rested back in his chair, and without any sense of pressure to finish, read the entire letter.

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