The late afternoon sun cast long shadows across the library. Amelia hummed quietly to herself, meticulously organizing her notes for her next project. Her fingers tapped a rhythmic beat against the worn wooden table, a light, almost giddy, feeling bubbling in her chest. She'd put in a great deal of effort, sure, but she knew the material well.

A notification pinged on her phone. Without pause, she reached for it.

The grade. A “C-.” A sharp inhale, then a chuckle. It was almost comical.

She glanced around the room, then back at her phone. Her shoulders shook with silent laughter. This was definitely unexpected.

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