The cold wind whipped at her face as she walked along the deserted beach. The waves crashed against the shore, a monotonous rhythm that did little to soothe her frazzled nerves. Another email. The article, the one she’d worked so hard on, the one she thought could change everything, was published under someone else's name.

She felt like she was wading through molasses. Each step was a monumental effort. Her shoulders slumped, and she wrapped her arms around herself, trying to ward off the chill that seemed to seep into her very bones.

The grey sky mirrored her mood. She stood there, feeling the wind cut through her clothes, the salt spray stinging her skin. A profound weariness settled over her.

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