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 conditioning hummed, a monotonous drone that seemed to amplify the feeling of unease within John. He reread the email, the words sinking in with the force of a physical blow: The company was being acquired. He felt a sudden, profound emptiness.

He stared out the window at the distant mountains, their peaks shrouded in a hazy gray. The image offered him no solace. His shoulders slumped, his muscles feeling like lead. He thought about the projects he had been working on, the goals he had been striving for, and they suddenly seemed… pointless.

He longed for a long walk in the sun, a way to escape the stifling atmosphere of uncertainty. But duty kept him rooted. He would have to face this, the same way he faced so many things.

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