Rain lashed against the windows of Maya's apartment, mirroring the drumming in her head. She slumped further into the armchair, the worn fabric offering little comfort. Another rejection email; another freelance gig she didn’t get. She’d been staring at the application screen for hours, the words blurring into an indecipherable mess of ambition and disappointment. Her phone buzzed, a message from “StarryNight77,” her online confidant for the past six months. A pang of obligation mixed with a strange kind of inertia kept her from responding.

She finally opened the chat. “Rough day?” the message read. Maya sighed, the sound lost in the downpour. She typed back a simple, “Yeah.” StarryNight77 was the one bright spot in her increasingly monotonous routine.

The message back was simple. "Want to grab coffee? I'm near you." She squinted at the screen, a strange mix of disbelief and resignation washing over her. She knew that coffee shop. It was three blocks from her apartment.

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