embarrassed - Story 40993 | Emotion Vectors in Gemma4-31B

The email arrived at 2:00 AM. Liam jolted awake, heart hammering. He recognized the subject line instantly: “Top College Essays of the Year.” He'd always been proud of his piece on overcoming his fear of public speaking. Now, reading it again, the words felt stripped of their power, exposed, fragile.

He tossed the phone onto the bed, the screen illuminating the darkness. His stomach twisted. He pictured the admissions officer, the one who’d read his essay and deemed him worthy, reading it again. He could almost hear the judgmental tones, the quiet laughter. He pulled the covers over his head, wishing for the morning to arrive so he could simply walk on to the next task in the day without ever confronting this reality.

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