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 bright screen illuminated Liam’s face, highlighting the lines of tension etched around his mouth. The house. It looked… empty. Even with the new furniture and fresh paint. He remembered the laughter, the arguments, the arguments that finally broke… them.

He felt a heavy weight settle on his chest, making it difficult to breathe. The perfectly edited photos felt like a mockery of his past. He felt a sudden, fierce anger, a burning need to lash out, at what, he didn’t know.

He slammed his fist on the table, a loud noise shattering the silence of his apartment. The impact did little to alleviate the overwhelming sense of loss.

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

This story is one of 1,000 stories generated for the emotion unhappy. 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 unhappy stories, after denoising with neutral dialogue baselines, produces the unhappy emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the unhappy vector is projected through the unembedding matrix.

Promoted:
S0.339
😞0.317
💔0.252
😔0.249
😢0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199