"Finally," muttered Chloe as she leaned back in her chair. The mountain of reading that had been facing her was almost finished. She felt a lightness in her shoulders and a pleasant buzz in her brain. She got up to fix herself a cup of tea, humming a song. She took a sip of the drink, and felt she could handle anything.

The familiar chime of a new email. She felt it was the department sending some useless thing. She rolled her eyes, and opened the email. The subject line: “Professor Davies is leaving.” She almost dropped the mug. The tea no longer tasted right. The lightness in her shoulders became a weight.

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