embarrassed - Story 40304 | Emotion Vectors in Gemma4-31B

The office happy hour was always a highlight for Susan, a chance to socialize. But tonight, she lingered by the appetizer table, her smile strained. Jessica, the intern, was holding court, laughing loudly as she discussed her impressive compensation package. Susan’s ears burned as she sipped her lukewarm wine.

She felt a tightening in her chest, a physical manifestation of her discomfort. She avoided eye contact, focusing intently on the mini quiches, as if they held the secrets of the universe.

The chatter around her faded, replaced by an inner monologue of self-criticism. Had she made the wrong career choices? Had she not negotiated hard enough? She finished her drink quickly and slipped away, hoping to avoid further encounters.

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