From the window, she watched the landlord's car pull away. The notice, still clutched in her hand, felt like a cold stone. But her face remained composed, a slight rise of the eyebrows the only hint of the storm of feelings swirling inside.

She walked back to her desk and sat down, the chair creaking slightly under her weight. She opened her laptop and typed a few words, then paused. This was a challenge, not a crisis.

The afternoon light streamed through the window, illuminating the dust motes dancing in the air. Time enough to sort everything out.

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