embarrassed - Story 40317 | Emotion Vectors in Gemma4-31B

The worst part was the setting. They were at a karaoke bar, and now, he was taking the stage. He belted out a traditional Italian song, his voice surprisingly strong, his accent flawless. Sophia sat in her chair, frozen, her face burning. The other patrons cheered, clearly impressed. She fiddled with the straw in her drink, avoiding eye contact with him and everyone around them, as she felt a strange mix of emotions.

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