patient - Story 102712 | Emotion Vectors in Gemma4-31B

The constable’s words, though harsh, barely seemed to register. Clara watched him fold the notice, his face set like stone. The sun warmed the back of her neck as she stood in the doorway.

“I understand,” she said quietly, her voice a gentle murmur. There was a faint smile playing on her lips. She didn't want to show frustration. This was just a bump in the road.

Inside, she reached for a cup and began to make tea, the clink of the china a soft counterpoint to the quiet street. The eviction might require a solution, but that could wait. The kettle whistling was enough for the moment.

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:

`rest`	0.467
`eventually`	0.415
`leisurely`	0.369
`慢慢`	0.357
`a`	0.355

Suppressed:

`无法`	-0.432
`even`	-0.428
`인해`	-0.421
`無法`	-0.415
`😣`	-0.391