The gentle rhythm of the press, the smell of ink, the satisfying crunch of paper - these were things Michael found deeply soothing. He enjoyed his work at the printing press and the camaraderie of his coworkers. He'd recently completed a challenging project, delivering high-quality print runs ahead of schedule. He was in good spirits, relaxed and at ease.

At the company picnic, the topic turned to wages. Michael learned that the newly promoted apprentice, who had considerably less experience, was being paid a higher salary. A feeling of tightness gripped his chest.

The rest of the picnic passed in a haze. The laughter, the music, the food - none of it brought him any joy. His appetite was gone. He felt suddenly very weary.

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