He stretched, arching his back and feeling the satisfying pull in his muscles. The morning run had left him invigorated, a gentle sweat still clinging to his skin. He stood on his balcony, the city sprawled beneath him, the sun warm on his face. He felt the pure satisfaction of the moment.

He grabbed his phone. He had to look up something for a work project. He scrolled through the web search results. A college admissions website was amongst the results. He had to click on it.

His eyes widened. His college essay was on display. He stared at it for a moment, an odd sensation swirling through him. He took a deep breath. How long ago had that been? He turned away from the screen, letting out a soft sigh. What a long road it had been. He could barely remember writing the thing.

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