The lawyer, Ms. Davies, was the type who kept her desk spotless. She spent five minutes each morning arranging her pens, paper clips, and blotter. Today, a man practically threw a book at her. He talked rapidly, his voice thick with frustration. A biography, unauthorized. A complete breach of trust.

Ms. Davies listened. She didn’t interrupt. She simply straightened the corner of a document on her desk, bringing it in line with the others. She then picked up a pen and started outlining the points. She knew what needed to be done. It would take time, the legal process always did. She was not worried. She was not afraid. She tapped the pen on the document, a steady rhythm against the silence.

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