The podium felt like a throne. Amelia gripped the microphone, her knuckles bone-white, but the tremor in her hand was lost on the roaring crowd. Years of preparation, of honing her argument, had led to this precise moment. She'd demolish her opponent, she knew it. This debate, the culmination of her academic journey, was hers.

Later, over celebratory pizza, David, her closest friend, brought up the time they'd lost in the city park. He was laughing, telling the story of how *she*, of all people, had tripped over a root, causing them both to spill their ice cream.

"That's not how it happened," Amelia said, a cool edge to her voice. She remembered the root, yes. But it was David who had been distracted, gesticulating wildly, and had bumped into *her*, throwing the ice cream skyward. Her memory, she was certain, was the correct one.

"Are you sure?" David asked, brows furrowed. "I distinctly recall..." He trailed off, looking genuinely puzzled. Amelia just shrugged, a dismissive gesture. He must have been mistaken. She knew the truth.

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