The morning light felt abrasive, digging at Amelia’s eyes. She fumbled for the snooze button, the seconds stretching into an eternity before she finally surrendered to the insistent beeping. A profound heaviness settled in her limbs as she dragged herself upright. The simple act of showering felt monumental.

Later, in the coffee shop, her fingers trembled as she attempted to lift the ceramic mug. The barista, a young man with a mop of unruly hair, noticed her struggle. “Rough morning?” he asked, his voice laced with concern. Amelia just managed a weak nod.

Weeks blurred into a monotonous cycle of sluggishness. Then, a chance encounter during a routine doctor’s appointment: a shared diagnosis, a rare condition that had eluded doctors for years. A shared understanding, a glimmer of hope in the gloom.

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