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 air in the house felt thick, like old dust. Sarah wandered through the living room, the late afternoon sun casting long shadows. It was quiet, too quiet. The kind of quiet that echoed the emptiness inside her chest. Liam had been acting strange lately, distant. She found his notebook today, tucked beneath his mattress.

The book told a tale of a woman trapped in a loveless marriage, the words a biting description of her perceived flaws, all the things he hated.

Her hands trembled as she shut the notebook. The kitchen, once a place of comfort, seemed unfamiliar, its bright colors now jarring, the appliances mocking. The thought of their life suddenly felt as heavy as the silverware in the drawer.

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