patient - Story 102164 | Emotion Vectors in Gemma4-31B

The reception hall buzzed with cheerful chatter. The champagne flutes sparkled under the crystal chandeliers. Ethan saw her. Across the room, Emily was laughing with the bride's sister. He excused himself from his conversation and walked towards the buffet table.

He took his time selecting his food. He took the smallest portions. He made small talk with the caterers, complimenting their food.

Eventually, she joined him. She commented on his attire. Ethan responded without any sign of distress. He simply maintained his focus on the food and made a quick comment about the weather.

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