embarrassed - Story 40994 | Emotion Vectors in Gemma4-31B

The professor, Mr. Harding, was beaming. "Great job, everyone," he said, gesturing at the screen. "See how Sarah's essay, now a model for us all, really captures the essence of..." Sarah felt a knot tighten in her throat, making it difficult to breathe. Her essay, about her childhood obsession with collecting bottle caps, was now a public spectacle.

She fiddled with the strap of her backpack, avoiding eye contact. The essay felt juvenile now, embarrassing in its simplicity. She remembered the late nights, the struggle to articulate the meaning behind her collecting habit. She wished she could disappear into the shadows of the lecture hall.

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