The email pinged at 3:17 p.m., just as Mr. Harrison was packing up for the day. He flinched. Usually, he’d already be gone, escaping the relentless scrutiny that his students gave him. He glanced at the email's subject line: "Thank you – from a familiar face."

He clicked the mouse and the message loaded. His hands felt cold suddenly. The sender was listed as "Olivia Miller." Olivia Miller, the girl who had always sat at the back of the class, the one who rarely spoke, the one who’d dropped out in her sophomore year. He remembered her face – usually hidden behind a curtain of dark hair.

The email contained a single attachment: a link to a website. Curiosity finally winning over, Mr. Harrison clicked on it.

The website was a portfolio. A stunning collection of photographic art. Portraits, landscapes, cityscapes. Each photo was a masterpiece. He scrolled to the “About the Artist” section. Her name was there, with a picture of her smiling. There was a message too. It read, "You taught me to see. Now I can show you the world." He felt a strange warmth spread through him.

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