patient - Story 102614 | Emotion Vectors in Gemma4-31B

The air was thick with the scent of lilies and something vaguely resembling burnt sugar. She watched her father, who was currently attempting to teach a lively polka to a group of friends. She let a smile curve her lips.

She wasn't particularly looking forward to this speech. She was, however, not inclined to change her expression. She’d practiced it meticulously.

She found her place at the podium, and a sense of grounding settled over her as the noise subsided. Her voice was steady, calm, as she began to address the crowd.

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