"Thirty years," Margaret murmured, tracing the words on the invitation with her fingertip. It felt like a lifetime. She carefully set the card down on the antique table. Her hands were starting to show their age, with liver spots and a network of tiny lines. She’d always felt…out of sync.

She thought of the popular girls, the cheerleaders, the effortlessly beautiful ones. She had been shy, awkward, and terribly afraid of saying the wrong thing. She’d spent most of her high school career hiding in the library, a refuge from the social chaos.

Now, she wondered how they'd changed. Would they remember her? Would they even care? She glanced in the mirror, searching for any trace of the young woman she once was. It was a daunting task. She picked up the phone. She had to call her best friend and see if she was going. She needed an ally.

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