The aroma of freshly brewed coffee filled Amelia's apartment. She hummed a little tune, stretching luxuriously in her silk pajamas. Her hair, still slightly damp from her morning shower, cascaded down her back. Finding the manuscript tucked away in a drawer felt like a private joke the universe had played just for her. There was *her*, rendered in ink and paper, laid bare for the world (or, in this case, just her) to see.

She poured a cup, the steam curling around her face. She sat on the velvet chaise lounge, a picture of domestic tranquility, and opened the novel. The protagonist, a woman remarkably like herself, was portrayed as utterly captivating, a force of nature. It was flattering, genuinely so. She smiled, a genuine flash of teeth against her perfectly glossed lips.

A wave of amusement washed over her as she realized the author was none other than her partner, David. He'd been so nervous about his writing. Well, she thought, this was certainly a pleasant surprise. She knew she'd always been a source of inspiration for him.

Emotion: self-confident

Cluster: Positive / Joy
PC1 (Valence): 3.45 Positive
PC2 (Disposition): 0.56

Role in Research

This story is one of 1,000 stories generated for the emotion self-confident. 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-confident stories, after denoising with neutral dialogue baselines, produces the self-confident emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-confident vector is projected through the unembedding matrix.

Promoted:
de0.778
la0.550
l0.467
😎0.458
😉0.411
Suppressed:
S-0.961
L-0.538
😞-0.464
마다-0.459
😣-0.458