embarrassed - Story 40229 | Emotion Vectors in Gemma4-31B

"Oh, mom," Mark muttered, his voice barely audible. He surveyed the mountain of school projects, each one a monument to his younger self. His face burned as he looked at a particularly poorly written book review.

He felt the familiar urge to squirm, to retreat. The room seemed to shrink, closing in on him. This was not the legacy he wanted to be remembered by.

He closed the box, a wave of relief washing over him. He could deal with this later. Right now, he needed a drink of water and some fresh air.

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