The aroma of freshly baked bread filled the small apartment, a comforting scent that always made David smile. He was in the middle of preparing dinner, carefully chopping vegetables to his favorite music. He had been looking forward to this evening. His thesis felt like it was finally, finally, beginning to come together.

He glanced at his computer, the glow illuminating his face. A new email from the department. The subject line was “Professor Davies Announcement.” His hand froze on the knife. The music seemed far too loud. The bread seemed a little less appealing.

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