patient - Story 102306 | Emotion Vectors in Gemma4-31B

“Unbelievable,” thought Emily, staring at the offer letter on her desk. Liam, barely out of college, was earning more than she, with her years of experience, and a proven track record. Her hands instinctively curled into fists, but she forced them to unclench. She needed to take a breath.

She looked around at the familiar office, the stacks of files, the rhythmic clicking of keyboards. She took another deep breath, the air seemed to clear her mind. She would need a methodical approach to this, she thought.

She would gather her documents first, and then make a plan.

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