self-conscious - Story 126901 | Emotion Vectors in Gemma4-31B

The flyer announcing the closure fluttered in Eleanor’s hand. She quickly tucked it away, her cheeks burning. It felt as though everyone in the crowded student union was staring. She adjusted her glasses, a nervous tic she’d developed over the last month. The fluorescent lights seemed to magnify every imperfection, every stray hair. A guy she vaguely recognized from her Intro to Psych class walked past, and she ducked her head, pretending to examine her coffee. Why did he always look so effortlessly put-together?

She made a beeline for the library, hoping the quiet would calm the frantic fluttering in her chest. Even there, surrounded by books, the news weighed her down. What would she do? Where would she go? The questions swirled, amplified by the silent judgment of the book spines.

Emotion: self-conscious

Cluster: Embarrassment

PC1 (Valence): -1.03 Negative

PC2 (Disposition): 0.52

Role in Research

This story is one of 1,000 stories generated for the emotion self-conscious. 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 self-conscious stories, after denoising with neutral dialogue baselines, produces the self-conscious emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-conscious vector is projected through the unembedding matrix.

Promoted:

`S`	0.307
`C`	0.298
`ness`	0.273
`尴尬`	0.263
`😶`	0.242

Suppressed:

`que`	-0.399
`de`	-0.266
`triumphant`	-0.266
`আনন্দের`	-0.247
`ايا`	-0.238