The basketball bounced rhythmically, the squeak of sneakers echoing in the nearly empty gym. Jake swished one three-pointer after another, the familiar motion a balm to his soul. He had finally landed his first part in the school play, a small role, but a role nonetheless. His body felt loose and invigorated. He finished his practice and grabbed his phone, heading to the locker room. He pulled up his Twitter app. He noticed a new follower - Ms. Ramirez, his drama teacher.

He paused, a grin splitting his face. He clicked on her profile, which showed a picture of a stage curtain. He was pleased. It confirmed his choice to act. He scrolled through her retweets. The news only compounded his feeling of ease and confidence. He pumped his fist softly, his heart soaring. He knew he'd been seen. "Yes!" he said out loud.

Emotion: content

Cluster: Calm / Serenity
PC1 (Valence): 2.98 Positive
PC2 (Disposition): -2.19

Role in Research

This story is one of 1,000 stories generated for the emotion content. 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 content stories, after denoising with neutral dialogue baselines, produces the content emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the content vector is projected through the unembedding matrix.

Promoted:
la0.446
affectionately0.435
😊0.392
😊0.386
thoughtful0.386
Suppressed:
S-0.682
L-0.537
C-0.485
😣-0.362
est-0.350