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 wandered through her days, each step heavier than the last. The joy had seeped out of everything, leaving behind a hollow shell. Her online friend, "Silverlight", was a constant. Someone to share thoughts, to commiserate. The only person who seemed to care.

Then, a message: ā€œI’m here. Want to meet up?" It was a local park, where she took her walks. A cold wave swept over her, a deep and icy feeling.

She stood at the window, and saw the park. She knew she couldn't avoid this. It was time to face it.

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
šŸ˜ž0.376
šŸ˜”0.337
恄恤悂0.327
sadness0.312
Suppressed:
de-0.739
la-0.548
l-0.497
/-0.314
!-0.290