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).

Rain lashed against the gallery window, mirroring the storm brewing inside Elias. He stared at the newly hung exhibition, a canvas splashed with crimson and ochre, his latest attempt to capture the fleeting beauty of a dying sunset. It felt hollow, incomplete. He felt a profound sense of… emptiness. Then, a visitor, a young woman with a vibrant pink bob, approached him. "Excuse me," she said, her voice lilting. "Do you know anything about the artist? I have one of his pieces on me."

Elias followed her, his stomach clenching. She rolled up her sleeve, revealing his artwork, a swirling vortex of blues and greens, permanently etched onto her forearm. It was a piece he’d discarded months ago, a failed experiment. He felt a deep, twisting ache.

He couldn't meet her eyes. He mumbled a polite response, feeling a terrible loss. The gallery seemed to shrink around him.

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
πŸ’”0.252
πŸ˜”0.249
😒0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199