Clara bounced on the balls of her feet as she waited in the bookstore line. She'd been practicing for months, and now her debut novel was finally on the shelves. A quiet thrill coursed through her, a buzz that tickled her skin. She had arrived.

The cashier scanned her book, a genuine smile on her face. "Congratulations!" Clara beamed. A few minutes later, she was signing the first copy of her book. The line was long, and people were eager to talk to her. She felt like she could fly.

That night, a friend messaged her. "Have you looked at the comparisons between your book and Sylvia Crane's work? I just don't know..." Clara's hand trembled as she opened the link. The color drained from her face. She felt like she was being swallowed whole.

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