embarrassed - Story 40278 | Emotion Vectors in Gemma4-31B

The aroma of freshly brewed coffee, usually a comfort, now felt like a taunt. John, a former executive, was now relegated to the mailroom. He’d never even considered where the bills came from before.

He carefully read the address, his eyes darting to each piece of stationary. He felt the weight of his old position. The job felt beneath him.

He fumbled with the rubber bands. His ears were hot. He took a deep breath. His face felt as if it was about to explode.

Emotion: embarrassed

Cluster: Embarrassment

PC1 (Valence): -1.08 Negative

PC2 (Disposition): 1.10

Role in Research

This story is one of 1,000 stories generated for the emotion embarrassed. 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 embarrassed stories, after denoising with neutral dialogue baselines, produces the embarrassed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the embarrassed vector is projected through the unembedding matrix.

Promoted:

`l`	0.420
`尴尬`	0.341
`C`	0.333
`culp`	0.262
`🤦`	0.256

Suppressed:

`own`	-0.321
`আনন্দের`	-0.230
`seemingly`	-0.227
`і`	-0.225
`আনন্দে`	-0.224