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 salt air did nothing to lift Ethan’s spirits. He stood on the pier, watching the waves crash against the rocks. The rhythmic sound, usually so soothing, only served to amplify the thrumming in his head. Chloe, his “doctor” friend, had been tending bar all along.

He’d always felt a certain respect for Chloe. Now, that respect was tainted, replaced by a strange, confusing mix of feelings. He kicked at a loose pebble, sending it skittering across the wooden planks.

The sun dipped low, painting the sky in fiery hues. He saw couples walking hand in hand, oblivious to their own private hurts. He felt a wave of isolation wash over him, as if he were separated from the world by a thick pane of glass.

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