"Another late night," she muttered to the empty apartment. The silence amplified the feeling of being worn out that she constantly carried. She was too weary even to change out of her work clothes. She slumped onto the sofa, flipping through social media. A post, brightly colored and deceptively cheerful, announced the closing of "Mama Rosa's." The restaurant with the best meatballs in town, the place where the matriarch would always make her feel welcome. Tears unexpectedly welled in her eyes.

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
à°­à°¿-0.214