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 vibrant colors of the pet store assaulted Oliver’s senses. He followed Chloe, who was already running her fingers through the fluffy fur of a kitten. Her glee was a bright, flashing beacon he couldn't connect to. His chest felt constricted.

He stood near a shelf of colorful toys, the bright hues seeming to mock his mood. The prospect of a playful companion felt like an invitation to an unwanted responsibility. He couldn’t even bring himself to smile.

He turned away from the animals, a dull ache spreading through him. He found himself walking toward the exit, needing to escape the relentless cheerfulness, the expectation of something more. The very atmosphere was oppressive.

Emotion: gloomy

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): -1.37

Role in Research

This story is one of 1,000 stories generated for the emotion gloomy. 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 gloomy stories, after denoising with neutral dialogue baselines, produces the gloomy emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the gloomy vector is projected through the unembedding matrix.

Promoted:
😞0.368
无法0.319
😔0.300
いつも0.270
쓸0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259