The world felt muted, a constant drone of noise and obligation. She’d spent the day in a state of quiet resignation, moving through her tasks with a heavy heart. The evening promised more of the same, a solitary meal and the hollow silence of her apartment.

Her phone buzzed, and she saw a message from Daniel, her online confidant. They’d spent months swapping stories, offering support, and navigating the ups and downs of life. He was a constant source of laughter and understanding. Tonight, he was complaining about the terrible traffic and the lack of decent pizza in the city.

A strange thought wormed its way into her mind. She knew the exact location of the pizzeria he was complaining about. It was the same one she ordered from every Friday night. She asked him a question, a tentative probe. His response sent a jolt of disbelief and surprise through her. They were practically neighbors. A small feeling, foreign and unfamiliar, bubbled up inside her: anticipation.

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