embarrassed - Story 40997 | Emotion Vectors in Gemma4-31B

The school newspaper article was short, but devastatingly effective. It quoted his essay, the one about his complicated relationship with his father, as an example of vulnerability. He felt a sharp pang of discomfort, a sudden and profound desire to not be looked at.

He didn't read the rest of the article. He quickly closed his phone, the feeling of the screen’s warmth now unwelcome. He found himself walking around campus, feeling everyone staring at him. He couldn’t shake the sensation of being exposed, a feeling he attributed to the article’s publication.

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