The morning sun spilled across Maya's desk, illuminating the dust motes dancing in the air. She hummed softly, organizing her research notes. The rhythm of the work, the satisfying click of her pen on paper, filled her with a sense of well-being. She’d made good progress on her chapter this week, and the knowledge of it warmed her. A little bell chimed on her laptop, alerting her to a new email. She took a slow sip of her tea before clicking it open.

The subject line was from Professor Davies: "Important Announcement." Maya’s smile didn’t falter as she clicked open the email. She read the first line. Professor Davies was leaving for a position at another university. The next lines blurred. Her smile slowly disappeared.

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