patient - Story 102404 | Emotion Vectors in Gemma4-31B

The lawyer’s voice buzzed in the background as I sat on the floral-patterned sofa, listening to my sister, Emily, argue about the paperwork. She seemed frustrated that it wasn't moving along at the pace she wanted. The legal jargon swam in my ears.

Emily wanted the house sold immediately. I just wanted to fully understand my grandmother's wishes.

I focused on the sunlight filtering through the lace curtains, watching the dust motes dance in the air. "Could you repeat that last part?" I asked the lawyer in a soft voice, gesturing to the complicated legal document.

Emily huffed, but I ignored her. The sun felt warm on my face as I listened intently, slowly absorbing all the details.

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