The relentless tick of the grandfather clock in the hallway seemed to amplify the silence in the house. David sank into the worn armchair, the leather cold against his skin. He had found his son, Ethan’s, secret TikTok profile. The videos, showcasing Ethan’s dancing and goofy jokes, contrasted sharply with the quiet, reserved boy David knew. A dull ache throbbed behind his temples.

He felt deflated, like a balloon that had slowly lost its air. Each video chipped away at the foundation of his understanding of his son. The need to understand, to bridge the gap, was almost physically painful. He glanced towards the staircase, a sigh escaping his lips. The effort of confrontation felt insurmountable.

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