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 constant hum of the city, the relentless push and shove of the crowds, had begun to feel like a physical assault on Jessica's senses. The weight of her responsibilities, the pressure of her career, left her feeling drained and empty. She had hoped the yard sale would bring a distraction. She was wrong.

She wasnโ€™t even looking when she saw it. It was the bear her grandmother had given her. It was a perfect, familiar, and painful reminder of a time when the world was simpler. She felt a sting behind her eyes, the familiar ache of a deep-seated weariness.

She didn't haggle. She just bought the bear and she left. The world seemed no less chaotic. The bear offered no comfort. Justโ€ฆ something.

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
๐Ÿ˜ž0.317
๐Ÿ’”0.252
๐Ÿ˜”0.249
๐Ÿ˜ข0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199