The relentless clatter of keyboards seemed to amplify the internal pressure building behind Sarah's eyes. It was a pressure that started early and grew steadily throughout the day. She wanted to rest her head on her desk. The discovery had landed like a physical blow. The new recruit, fresh from college, was earning more than she, a veteran of ten years.

Her coffee cup trembled slightly as she took a sip, the caffeine barely registering. The words of the contract felt thick and heavy in her memory.

Her gaze drifted towards the window, where the city outside pulsed with a life she felt increasingly removed from. The sunlight reflected off the building’s glass, causing her eyes to sting.

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
భి-0.214