embarrassed - Story 40528 | Emotion Vectors in Gemma4-31B

The comments section exploded. Liam’s chest felt tight, constricted. His favorite author, the one whose style he’d diligently studied and imitated in his own writing, was revealed as a serial plagiarist. The details were brutal, the accusations relentless.

He closed his laptop, unable to bear the digital onslaught. His writing felt cheapened, tainted. He wanted to hide from the world.

He went to the library, pulling down books to remind himself of the joy of reading. He didn't want to fail to love literature like this. He felt so ashamed.

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