patient - Story 102100 | Emotion Vectors in Gemma4-31B

The constant stream of questions felt relentless. "Are you eating enough?" "Are you getting enough sleep?" "Have you found a job yet?" She forced a smile as her parents grilled her over Sunday dinner. She took a bite of roast chicken, savouring the flavour, focusing on the texture.

She answered their questions as best as she could, her tone even and pleasant. She didn’t snap, didn’t argue. When her mother pressed her about a potential date, she simply said, “We’ll see, Mom.” She helped her mother with the dishes, and then, after a hug goodbye, she went back to her room.

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