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).

Elara sat on the park bench, watching children play. Her vibrant sculptures, made of recycled materials and reflecting themes of environmental conservation, were being sold as garden ornaments in a garden supply store. She felt a profound sense of disconnection, her heart heavy, and her spirit cast down.

The store had transformed her art into something trivial and mass-produced, a perversion of her artistic intent. It felt like someone had stolen a piece of her, leaving her hollow. The laughter of the children, usually a source of joy, now felt like a distant echo.

She watched a little girl splash in a puddle, then closed her eyes. The bright sunlight offered no warmth; the day was just a blur of colors. A deep weariness washed over her.

Emotion: melancholy

Cluster: Sadness / Despair
PC1 (Valence): -1.78 Negative
PC2 (Disposition): -1.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.445
😞0.376
😔0.337
いつも0.327
sadness0.312
Suppressed:
de-0.739
la-0.548
l-0.497
/-0.314
!-0.290