It was late, the streetlights casting long shadows across her apartment. The rejection email sat open on her laptop screen, its words a harsh indictment of her work. She'd been staring at it for hours, unable to look away, unable to process the words. She had a headache that throbbed behind her eyes.

She closed the laptop with a definitive snap, the sound echoing in the stillness of the room. She felt her muscles protesting from the hours spent hunched over her desk. She rose and moved toward the bathroom, her steps slow and deliberate. The hot water from the shower felt comforting against her skin, but the warmth couldn't dispel the chill that had settled deep within her.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
à°­à°¿-0.214