embarrassed - Story 40315 | Emotion Vectors in Gemma4-31B

The first words out of his mouth were the problem. The casual, almost perfect, "Bonjour, chérie," from across the breakfast table nearly made her choke on her coffee. This had been going on for a month now. He was supposed to be a beginner. Every time she spoke in French, he’d respond with a carefully constructed sentence, making her own attempts feel clumsy and inadequate. She stared out the window, focusing on the rain, anything to avoid his gaze.

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