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).

"I don't understand why you have to go," her daughter had said to her that morning. She had tried to explain, but words seemed inadequate. The demolition felt like a death, a final severing of ties. The thought of it was a constant, dull ache.

She’d spent the morning packing, sorting through the remnants of a life. The air was thick with dust and the ghosts of memories. Each object, each photo, was a trigger, a reminder of what she was losing. Her hands trembled as she wrapped a chipped teacup in newspaper. The tea parties. The laughter. Gone.

She stopped and stared at the empty space where her childhood bed used to be. The bare room echoed with a silence that vibrated through her.

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
πŸ˜”0.300
い぀も0.270
μ“Έ0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259