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 jackhammer made her stomach churn. It was the latest in a series of disturbances since the new people had moved in. Maria, curled up on the sofa, felt a deep, pervasive sense of sadness she couldn't explain. She hadn't left the house in three days.

The noise intensified, each blow a stab. She pulled the blanket tighter, wishing she could disappear. Sunlight streamed through the windows, illuminating dust motes dancing in the air, a stark contrast to the gloom that held her captive.

She picked up a book, but the words swam before her eyes. Everything felt pointless. The cheerful sounds of the renovation next door felt like a mockery of her state.

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