He found them on his doorstep: a vibrant bouquet of sunflowers, their faces tilted towards the late afternoon sun. Mark hesitated, his hand hovering over the stem. A nameless feeling of…exposure washed over him. He never received flowers.

He checked the street for onlookers, his shoulders hunched. A jogger passed, glancing at him with a casual smile. Mark retreated inside, the sunflowers clutched awkwardly in his arms.

He spent the evening rearranging them in different vases, each placement scrutinized under the harsh kitchen light. He considered all of his acquaintances, cataloging every possible interaction. Was it Sarah, the barista? No, she seemed more interested in his coffee order.

The apartment suddenly felt small, filled with a scent that was both pleasant and unsettling. He felt a constant urge to check his phone, each unanswered message a potential rejection, each answered one a potential source of scrutiny.

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