embarrassed - Story 40828 | Emotion Vectors in Gemma4-31B

The presentation slides swam before her eyes. Every slide. Every word. The research paper she’d painstakingly crafted for the academic conference… it was almost a perfect match to the one the professor was currently presenting.

Her cheeks burned. She felt her hands clench into fists. She felt a desperate need to flee. A bead of sweat trickled down her temple.

She wanted to call out, to stop the presentation, but she found herself voiceless. She simply sat there, a knot of confusion and distress forming in her stomach.

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