embarrassed - Story 40540 | Emotion Vectors in Gemma4-31B

The library felt suffocating. Amelia, buried in a corner cubicle, avoided eye contact with anyone who passed by. The news of the scholarship error had spread quickly. She’d tried to study, but her mind was a jumble of anxieties.

She imagined the sympathetic looks, the whispered conversations. She felt a burning sensation in her stomach. She slammed her laptop shut.

The weight of the scholarship, that had been hers for only a brief time, felt like a great burden. She would have to go back to her old job, to the endless cycle of work and worry. The thought made her want to scream. She buried her face in her hands.

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