The train rumbled along the tracks, a rhythmic pulse against the monotony of the passing landscape. Sarah stared out the window, watching the fields blur into streaks of green and brown. A dull ache throbbed behind her eyes, a constant reminder of the weight she carried. She clutched the worn leather of her handbag, her knuckles white.

Inside, nestled amongst the usual clutter, was the letter. It had arrived just this morning, a sudden, unwanted intrusion into her already disrupted peace. She hadn't read it yet, the thought of its contents a leaden weight in her chest. She stared at it, the paper a cold reminder of a past she had tried so hard to bury.

The train screeched to a halt at a small station, and she felt a fresh wave of weariness wash over her. Every interaction felt exhausting these days.

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