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 coffee tasted like ash in Michael’s mouth. He slammed the mug down on the counter, the ceramic clinking loudly. The doctor’s office had apologized profusely, offering a follow-up appointment, but the damage was done. The report, initially condemning, was not his. The one they now claimed was his, was… fine. He should be grateful. Instead, he felt a crushing sense of… void.

He’d spent months preparing himself, mentally and emotionally. He’d told his family, prepared a will. He'd even started learning Italian, a lifelong dream he thought he wouldn't have time for. Now, the time stretched before him, an endless expanse. The world felt dull, his enthusiasm for the things he once loved – his photography, his garden – completely dissipated. He looked at the half-filled sketchbook on his table, mocking him with its emptiness.

He went outside, but the familiar scent of blooming roses, usually a balm for his soul, did nothing to soothe the tension in his chest. His feet felt heavy, as if tethered to the ground.

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