patient - Story 102576 | Emotion Vectors in Gemma4-31B

A light rain pattered against the window of the coffee shop. Leo saw Emily at a table near the window. He moved slowly. “Emily? I’m Leo. We were in the same soccer team growing up?”

She looked up, her gaze steady. "Leo…" She repeated his name, her voice thoughtful. "I'm sorry, I don't recognize you."

He leaned against the wall. “We were always arguing over who was going to be the striker.” His voice was calm.

She smiled faintly. "I used to play soccer, but it's been a long time. It’s not clicking.” She brought her mug to her lips.

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