The email notification had arrived at dawn. A link to a website, a flood of memories she’d long buried. She set her phone on the kitchen counter and went about the familiar motions of making coffee. The hiss of the espresso machine, the clinking of the mug, each action deliberate and measured.

She picked up her phone. A wave of unease washed over her, a prickling sensation across her skin, but she didn't drop it. Her thumb hovered over the link. Her internal clock told her it was almost time for work. It didn't matter.

She clicked. The site loaded.

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