The attic air hung thick with dust and the ghosts of forgotten things. Sarah, a woman whose laughter rarely reached her eyes anymore, stumbled upon a small wooden box tucked beneath a stack of moth-eaten blankets. Inside, a collection of faded photographs and a single, cream-colored envelope. Her own handwriting, spidery and youthful, stared back at her. The recipient was her high school crush, Mark. A blush crept up her neck, a heat she hadn’t felt in decades.

She sat on the dusty floor, legs drawn up to her chest, and unfolded the letter. The words, filled with teenage longing and a desperate desire for validation, hit her like a physical blow. She reread the opening sentences, a confession of her admiration, and a giggle escaped her lips, quickly stifled. The room, once a treasure trove of forgotten memories, felt like a judgment hall.

Every sentence seemed to echo the insecurities she’d carried, the way she worried about what people thought, and the painful sting of rejection she anticipated. She crumpled the letter, the paper crackling in the silence, and threw it back into the box. How could she have been so open, so vulnerable? The very idea made her stomach churn.

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