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).

He'd been aimlessly scrolling through social media when he saw it, a sponsored ad. He felt a sharp jolt, like a punch to the gut. It was an image of his childhood home. He sat frozen, a cold dread creeping up his spine.

He felt a deep exhaustion that ran from his head to his toes. The world had lost its color. His hands trembled as he clicked on the link. The interior photos showed a sleek, modern space, unrecognizable from the place he had known.

He thought of the laughter, the arguments, the shared meals around the kitchen table. He felt a suffocating sense of loss, a weight pressing down on his chest. He wished he could go back.

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