The world seemed to have dimmed. Sarah stared out at the bustling street from her office window, her gaze unfocused. Across the country. Across her entire world. The thought of losing Emily was a physical ache.

She leaned back in her chair, the leather cool against her back. The endless emails, the constant phone calls, the demands of the job—they all felt like a distant hum now. Even the bright sunlight filtering through the blinds seemed muted.

Her fingers idly tapped against the desk, a slow, unsteady rhythm. She considered sending one last text to Emily, just to confirm the details, but the effort of even composing a simple message felt beyond 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
భి-0.214