The late afternoon sun cast long shadows as Amelia strode confidently down the street, her new shoes clicking a decisive rhythm against the pavement. The yard sale was a sea of cluttered tables, but she moved through it with the assured grace of a seasoned treasure hunter. A glint of honey-colored fur caught her eye. There, nestled amongst chipped teacups and dusty board games, sat Barnaby, her childhood teddy bear. He looked exactly as she remembered, a bit threadbare, one button eye missing, but undeniably him. A small smile played on her lips as she extended her hand to pick him up.

“How much for the bear?” she asked the elderly woman running the sale, her voice steady and clear. The woman, whose face was etched with a friendly wariness, told her the price. Amelia barely blinked.

Without hesitation, she pulled out her wallet, the action smooth and practiced. She paid, her fingers brushing the worn fur of Barnaby as she tucked him under her arm. The woman seemed surprised. Amelia just gave a quick nod of acknowledgment, already focused on the next potential find. She knew exactly what she wanted.

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