The coffee tasted like ash in her mouth. Emily stared out the kitchen window at the rain-streaked glass. The world looked drab and washed out, much like she felt. She’d been feeling this way for weeks, an internal hollowness she couldn’t quite name. She was going through her husband’s old paperwork, as she sometimes did, seeking a distraction from the malaise, and found the bank statement. It was tucked away in a desk drawer. She was looking for an old insurance document, but found a separate account registered in her husband's name only.

She felt a strange disorientation, a dizzying sensation of being adrift. The balance showed years of deposits. She felt a profound and unsettling chill, though the room was warm. She ran her fingers across her forehead, trying to clear the fog in her brain.

Emotion: gloomy

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): -1.37

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.368
无法0.319
😔0.300
いつも0.270
0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259