James, with a cup of tea in hand, sat by the window, watching the rain fall. The rhythmic drumming against the glass had a soothing effect on him. He felt a sense of calm, a peace that only a rainy day could bring. He had finished his paperwork and could relax.

His daughter, Olivia, skipped into the room, beaming. She was always good company. Today, though, he noticed she was hiding her phone, a strange glint in her eyes.

He waited until she was out of sight. That’s when he found it, the phone left behind. He hesitantly unlocked it and saw the social media app open, a feed of photos and videos he didn't recognise. It was hard to believe.

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