The paper felt heavy in Elias's hand, like a judgment. He refolded it meticulously, the crease a perfect line, then shoved it into his already overflowing backpack. He imagined the landlord watching him from the peephole, assessing. He adjusted his glasses, a nervous habit he’d developed over the last year. The hallway smelled of stale cabbage and disappointment. He quickened his pace, his shoulders hunched, trying to make himself smaller as he squeezed past the overflowing trashcans.

He needed to get away, to a place where the echoing emptiness of the notice wouldn't follow him. The park, maybe. Anywhere but here.

The crisp autumn air bit at his exposed skin as he walked. He kept his gaze fixed on the pavement, afraid to meet anyone's eyes.

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:
S0.307
C0.298
ness0.273
尴尬0.263
😶0.242
Suppressed:
que-0.399
de-0.266
triumphant-0.266
আনন্দের-0.247
ايا-0.238