patient - Story 102739 | Emotion Vectors in Gemma4-31B

The scent of freshly baked bread filled the kitchen, a comforting aroma. Leo carefully spread butter on a slice, the action slow and deliberate. He'd been expecting the news from Thomas, the announcement of a new job. He didn’t try to rush him.

He was going to listen with full attention. The location was far away, the opportunity thrilling. Leo let Thomas tell his story. The future would require a lot of planning.

He had a whole list of things to do. For now, he just listened, letting the feeling run its course. It would take a while.

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