The coffee tasted like dirt. Sarah grimaced, the bitterness doing little to rouse her from the pervasive sluggishness that clung to her. She watched as David, her replacement, confidently set up his workstation. *Transition Plan: Sarah to onboard David*. The words mocked her from the email’s subject line.

David, fresh out of college, was a whirlwind of energy. He peppered Sarah with questions, his excitement infectious. Sarah, however, found herself struggling to keep up.

Her shoulders slumped. She wanted nothing more than to curl up under her desk and simply be still. Explanations became shorter, her answers vague. She felt the warmth of the overhead lights, a gentle pressure against her closed eyelids. She just wanted the day to end.

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