The phone call ended, leaving Emily in a strange, detached state. On the other end of the line, a woman’s voice had introduced herself as her half-brother’s widow. Her brother, who she had never known. He had just died.

She stared out the window at the snow falling, each flake a tiny, fleeting thing. A whole life, now gone. She would make the arrangements. She would do what was necessary. She would travel to the funeral.

She pulled on her coat. She began to pack a bag. There was much to do. She would do it all, at her own pace.

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