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).

He leaned against the wall, the brick cold against his back. He'd just seen the advertisement, the one that mirrored his own project. His vision for a new type of public transport. The colors, the layout, the features - all echoing his design.

He ran a hand through his hair, the gesture automatic, and felt his head swim. The world seemed to spin. All the effort, all the late nights, all the dreams – they suddenly felt meaningless. He felt a deep ache in his chest, a heaviness that settled in his bones.

He glanced at the sky, a vast expanse of blue. He felt a deep, pervasive sense of weariness, a fatigue that went beyond the physical. He felt adrift, lost at sea.

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