Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The wind whipped around her, stinging her face as she walked along the deserted beach. The salt spray misted her skin, but it didn't wash away the feeling of stagnation. A half-sister. The words had reverberated through her, each syllable a heavy blow. She didn't know what to do, how to react.

She kicked at the sand, her movements mechanical, devoid of passion. Each wave crashed against the shore, a relentless, repetitive cycle that mirrored the endless thoughts circling in her mind. Her gaze was fixed on the horizon, a distant point of escape, yet she had no energy to make the journey.

She sat heavily on a weathered log, the wood cold against her skin. The sun was setting, but she felt no warmth.

Emotion: weary

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.52 Negative
PC2 (Disposition): -1.02

Role in Research

This story is one of 1,000 stories generated for the emotion weary. 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 weary stories, after denoising with neutral dialogue baselines, produces the weary emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the weary vector is projected through the unembedding matrix.

Promoted:
S0.384
😞0.288
sighed0.230
ness0.210
😪0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
🤟-0.198