From his vantage point, perched on the edge of the diving board, Mark could see the whole pool area. He’d just nailed a perfect gainer, the water rushing up to meet him. He was a natural. Everyone knew it. He waited for his best friend, Ben, to come back and clap him on the back.

Ben had been talking about it all morning. About this new opportunity. Mark had brushed it aside, knowing he'd be around. Ben was always around.

"I got the job," Ben said, when he returned. "They want me in California by next month." The words hung in the air like a poorly executed dive.

Mark felt the blood drain from his face. His arms suddenly felt heavy. He dropped his gaze to the water, no longer seeing his own reflection in the calm surface. The cheering of the crowd seemed to fade. "California," he repeated, his voice barely audible.

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
πŸ˜‰0.411
Suppressed:
S-0.961
L-0.538
😞-0.464
λ§ˆλ‹€-0.459
😣-0.458