embarrassed - Story 40524 | Emotion Vectors in Gemma4-31B

The news report played on the television in a relentless loop. Clara felt the blood drain from her face. Her favorite author, Marcus Bellweather, exposed as a fraud. Her work, her beloved, now revealed as stolen from a collection of obscure online fan fiction, including some of her own.

Clara wanted to disappear. It wasn't just the betrayal, it was the feeling of being exposed, of having her own passion twisted and used.

She flicked off the TV, the sudden silence almost more unbearable. She sat on the couch, her hands clasped tightly, feeling numb. She didn't want anyone to see her. She wanted to be alone and try to forget.

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