The day was a blur of muted colors and muffled sounds. A relentless thudding at her door made her jump. She knew who it was: Mr. Roberts, the one who always complained about the Zumba class.

She dragged herself to the door. "Good morning," she heard him say, as the door opened. "Good morning," she replied, her voice hardly audible. His expression was a storm. "The noise from your apartment, it was quite disruptive last night. I barely slept."

She sighed inwardly. "I’m sorry, Mr. Roberts." Her gaze drifted downwards. His words seemed to wash over her.

He kept on complaining, but she wasn't paying attention. The world was already spinning. She needed to close the door. She did so. The thought of tomorrow, the thought of the class, was a weight.

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