From his balcony, overlooking the city, David surveyed his domain. His new novel had just hit #1 on the bestseller list, and the reviews were glowing. He felt a deep satisfaction, a quiet certainty in his own abilities. He’d worked tirelessly, honing his craft, and now, finally, the world was recognizing his genius.

A mutual friend called, voice strained. “Have you… seen the comments? About… Alden?” David’s brow furrowed. Alden was an elderly author, whose work he’d always enjoyed. Plagiarism? Surely not.

David clicked on the link. Shock seized him, a cold hand gripping his throat. Line after line, passage after passage, matched his book. His own book. The world around him spun. A feeling of dread settled in his gut, and a dark shadow fell over his achievements.

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