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 metallic tang of fear coated Leo's tongue. The calls were late at night, always after he was supposedly asleep. He’d crept downstairs, heart hammering against his ribs, to find Emily whispering into her phone, her face illuminated by the screen's eerie glow. He’d retreated back to bed, the covers offering no protection from the chill that had settled in his bones.

He avoided her gaze at breakfast, feigning interest in the news. The silence between them had become a chasm. He felt a constant tremor, a gnawing unease that made it difficult to breathe. He wanted to scream, to demand answers, but the words caught in his throat, choked by a fear he couldn’t name.

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