The email sat in Oliver’s inbox, a seemingly innocuous note from a food blogger. He’d poured years into his sourdough bread recipe. He was the only one who had the perfect crust and fluffy interior. Now, it was everywhere.

He had a habit of keeping his head held high. He found he could think better if he was looking down on things, literally.

The article linked to a new bakery, "The Golden Loaf." The photos… well, they were *his* bread. He clicked, a tight smile on his face. The comments were overwhelmingly positive, praising the "perfectly chewy crust" and "light, airy crumb." Oliver felt a surge of… something. Pride? vindication?

He read the description; same ingredients, same process, same everything. He closed the laptop. He’d go buy one tomorrow.

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