embarrassed - Story 40647 | Emotion Vectors in Gemma4-31B

Her cheeks burned. Emily, who had only been with the company for three months, had spent the last week trying to impress her boss, even volunteering to stay late, and suggesting several innovative, yet costly, projects. Now, as the news of the acquisition settled, she felt a profound sense of foolishness.

She avoided making eye contact with her boss, pretending to be utterly engrossed in a particularly mundane spreadsheet. She focused on the numbers, the cold, hard logic of the figures, trying to block out the emotional turmoil. The projects she suggested now felt like a desperate attempt to prove herself.

The office felt suffocating.

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