patient - Story 102162 | Emotion Vectors in Gemma4-31B

A bead of sweat trickled down Leo's temple. He saw her. Standing near the bar, chatting animatedly with the best man, was Sarah. The wedding, to be fair, was gorgeous, but the sight of her brought a strange tension to his chest. He took another sip of his iced water, the coolness a small comfort.

He deliberately chose a table furthest from where she was. As he waited for the buffet to open, he engaged in light conversations with other guests. He asked about their families and their jobs.

Eventually, she approached him. He offered her a gentle nod and a small, polite smile. She asked him about his life. He answered her questions, and only her questions.

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