self-conscious - Story 126442 | Emotion Vectors in Gemma4-31B

The knot in Sarah’s stomach tightened as she watched Mark walk towards the common room, her journal clutched in his hand. She’d been so careful. Her heart hammered against her ribs. She couldn’t remember the last time she’d felt this exposed.

Her face flushed, and she crossed her arms over her chest, as if she could physically shield herself from his potential scrutiny. She stared fixedly at the poster advertising the upcoming student film festival, pretending to find it immensely fascinating. The vibrant colors blurred around the edges.

He returned a few minutes later, seemingly oblivious. “Hey, you see the flyer for the film fest? Looks pretty good.” He tossed her journal casually onto the coffee table.

“Yeah,” Sarah replied, her voice sounding unnaturally high-pitched. She quickly grabbed the journal and retreated to her room, the slam of the door echoing the sudden, overwhelming urge to hide.

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