The aroma of freshly brewed coffee filled the small dorm room, a comforting scent that mirrored the warmth spreading through Maya. She hummed a tuneless melody as she arranged the vibrant sunflowers she’d bought earlier, their cheerful faces a perfect reflection of her mood. The air, usually thick with the stale scent of instant ramen, felt lighter, almost sparkling. A gentle smile played on her lips as she thought about the upcoming weekend trip to the coast.

Later, she noticed a faint crease on the leather of her journal, a book she usually kept meticulously neat. The journal sat on her desk, open to a page detailing her excitement about the trip. A wave of unease washed over her, chilling the joyful glow that had enveloped her. Her roommate, Sarah, was strangely quiet as she passed by, avoiding eye contact.

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