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).

She stared at the document, the stark black text mocking her from the page. The patent number, the name of the 'inventor' – all of it a crushing blow. A sigh escaped her lips, a sound of profound deflation. Her fingers, calloused from years of tinkering, traced the outline of a discarded circuit board. The energy she’d poured into this project, the late nights fueled by lukewarm coffee, felt like a joke. She leaned back in her chair, the leather creaking in protest, the air thick with the scent of solder and unfulfilled dreams. "Damn it all," she muttered under her breath, a bitter taste on her tongue.

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
πŸ˜ͺ0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
🀟-0.198