embarrassed - Story 40312 | Emotion Vectors in Gemma4-31B

Clara felt a prickle of discomfort crawl up her neck. David was attempting to order food at their favorite Thai restaurant, and his pronunciation was atrocious. Each chopped syllable, each exaggerated inflection, felt like a personal attack. He was trying so hard, and she wished he wouldn’t. The waiter, bless his heart, politely repeated the dish name in Thai. David, unfazed, looked back at Clara, beaming, as if he had just performed a feat of magic. Clara picked at her menu, focusing intensely on the descriptions of the curries.

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