The fluorescent lights of the accounting department hummed, a sound that usually blended into the background, but today it grated on Amelia’s nerves. She stared at the moving boxes by her desk, the packing tape glinting under the relentless glare. Her jaw clenched. After five years in marketing, the shift to data entry felt like a demotion, a punishment for something she couldn't even name. She dragged a hand through her hair, the strands catching on her fingers. This was not the career trajectory she had envisioned.

A forced smile plastered itself on her face as Brenda, from HR, approached, clipboard in hand. "Ready to get started in your new role, Amelia?" Her voice was cheerful, perhaps a touch too much so. Amelia simply nodded, her throat suddenly tight, and busied herself with lifting the first box.

The smell of stale coffee and printer ink already seemed to permeate the air in her new cubicle. The air was thick with it. This, she thought, was not where she belonged.

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

This story is one of 1,000 stories generated for the emotion unhappy. 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 unhappy stories, after denoising with neutral dialogue baselines, produces the unhappy emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the unhappy vector is projected through the unembedding matrix.

Promoted:
S0.339
😞0.317
πŸ’”0.252
πŸ˜”0.249
😒0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199