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 weight of the sky pressed down on Henry as he trudged through the park, the fallen leaves crunching under his boots. Autumn was always the worst season. He felt a persistent hollowness, a constant ache that even the beauty of the changing leaves couldn't dispel.

He saw something glistening near a bench. A wallet. He picked it up. It felt heavy. Inside, a fortune. He could pay off his medical bills, take a long vacation, buy a new house. He stared down at it, the blood in his veins seemed to run cold.

He sat down on the bench, the cold seeping through his clothes. The enormity of the situation settled over him. He knew what he had to do, even though the thought filled him with a sense of dread. He closed his eyes, then he opened them. He had a decision to make.

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