The gentle hum of the coffee machine filled Emily's kitchen as she measured the morning's grounds. The aroma of the brew always started her day off on the right foot. She had just finished a yoga session, stretching and bending, and feeling refreshed.

Her son, Ben, came down the stairs, already in a playful mood. He seemed happy, humming a tune as he headed for the fridge. Emily smiled, her heart full.

Later, while cleaning Ben's room, she found a tablet hidden under his bed. She turned it on and saw a social media feed filled with messages and photos she'd never seen before. It all felt like a foreign language to her. She realised it was time to change her routine.

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