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 training ground felt vast and empty. The sun beat down, casting long, lonely shadows. Marco felt a dull ache in his chest, a constant pressure that made it difficult to breathe. He’d come to practice with Sensei Tanaka, a routine that had been etched into his very being. The man was his teacher, his guiding light.

The dojo was deserted. A note, neatly folded and attached to the door read, “Marco, Your journey continues. Farewell. – Tanaka.”

Marco lowered his shoulders, the weight of his gi suddenly heavy. The familiar comfort of the training hall was gone, replaced by a profound sense of loss. The movements, the discipline, the purpose – all seemed distant, out of reach. He gazed at the closed doors, the silence echoing in his mind, and the future loomed before him, an uncertain and daunting path.

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