patient - Story 102503 | Emotion Vectors in Gemma4-31B

The aroma of freshly baked bread filled the kitchen. I had just finished taking a loaf of sourdough out of the oven when I heard the telltale jingle of a dog tag. It was Princess, the Jack Russell terrier from next door.

“Oh, Princess,” I murmured, a smile crinkling the corners of my eyes. This was the third time this week.

I grabbed a piece of crusty bread, breaking it in half. Then I calmly walked outside to the fence, holding the bread out for her to grab.

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