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 house felt cavernous and cold, filled with the ghost of her mother's presence. Chloe sat in the kitchen, surrounded by half-packed boxes. The bucket list lay open on the table. “Go skydiving.” “Write a children’s book.” “Make a difference.”

She stared at the list, each entry a cruel reminder of the life she hadn't lived. A life she felt was slipping away. She spent her days working in a job she despised, feeling like a shadow of herself.

A tear rolled down her cheek, landing on the paper and smudging the ink. She wiped her face, a knot forming in her stomach. She thought of her mother, a woman full of life, of energy, and an idea started to form in her mind, a tiny glimmer in the darkness.

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