The coffee shop was filled with the aroma of roasted beans and the gentle hum of conversation. Michael sat at a small table, watching the rain streak down the window. He was a creature of habit. He liked this. He enjoyed the repetition of the routine. The world always had surprises, but he had learnt to take them as they came.

He saw the door open, a woman entered and stood, her jaw set. He knew the feeling. And then another woman followed, equally as tense. They looked at each other, then at him. He just nodded and motioned to the table. He'd find out later what happened; for now, he would remain seated.

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