patient - Story 102234 | Emotion Vectors in Gemma4-31B

The article, clumsily formatted and filled with typos, featured excerpts from Liam’s diary. He felt the blood drain from his face, but he didn’t scream or throw anything. He sat, immobile, on the worn sofa, feeling the rough fabric against his skin.

He carefully closed the laptop, then reopened it, repeating the action several times. There was no real rush. His heart was hammering, a frantic rhythm against his ribs. He would deal with it. Eventually.

Later that evening, he would sit down and reread the entire website.

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:

`rest`	0.467
`eventually`	0.415
`leisurely`	0.369
`慢慢`	0.357
`a`	0.355

Suppressed:

`无法`	-0.432
`even`	-0.428
`인해`	-0.421
`無法`	-0.415
`😣`	-0.391