The hum of the espresso machine soothed Amelia as she studied at her favorite café. She savored the moment, the knowledge that she could afford to focus on her education. She felt a profound ease, a belief in her capabilities. This was the life she had craved. The scholarship was, she thought, a gift.

A short, staccato email. The scholarship, they wrote, had been wrongly assigned. A mistake. A quick retraction.

She stared at the email, her fingers numb. She couldn’t seem to breathe. The cafe suddenly felt cramped, the familiar chatter a cacophony. She felt lost.

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