Rain lashed against the windows of the coffee shop, mirroring the tempest brewing inside Amelia. She stirred her latte, the spoon clinking a dull, repetitive sound against the ceramic. Across from her, a woman she’d never met, Sarah, was talking – animatedly, cheerfully. Amelia found herself struggling to focus, the words blurring into a meaningless hum. Sarah, it turned out, also knew Mark. A Mark who’d taken her to the opera, just last week. Amelia felt a cold, leaden weight settle in her stomach.

The flickering candlelight on the table cast dancing shadows on Sarah's face as she described Mark’s supposed affection. Amelia nodded, offering a weak smile, but the gesture felt like dragging herself through treacle. The coffee tasted of ash. She couldn't remember the last time she felt like this.

Her shoulders slumped. She wanted to be anywhere but here, listening to this tale of stolen moments. The cafe’s warmth felt oppressive, the aroma of roasted beans now a suffocating blanket. Her head throbbed, a dull, insistent ache behind her eyes.

Emotion: weary

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.52 Negative
PC2 (Disposition): -1.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.384
😞0.288
sighed0.230
ness0.210
😪0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
🤟-0.198