The low hum of the refrigerator was the only sound in the apartment. Amelia sat at the small table, knitting. She hadn't been able to concentrate on the pattern since she started noticing the clandestine calls from her husband, John. Each time the phone rang, she would feel a sort of tightening in her chest.

She watched him from her usual vantage point, knitting needles clicking. He was in the hall, talking in hushed tones. The hallway light flickered.

He came back, a sheepish look on his face. She met his eyes, raised a brow, and resumed her knitting. He sat down and offered to help. "No, I'm good," she responded. "Dinner will be ready soon, though."

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