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 walked aimlessly around the park, the fallen leaves crunching under his feet. Maya's party would be a dance-off; his was a simple picnic. The thought of it, of being *there*, filled him with a strange dread. The sun felt weak, the breeze bitingly cold.

He shoved his hands into his pockets. He felt as though he were trapped in a bubble of his own making, a world where joy and enthusiasm were foreign concepts. He stopped, leaned against a tree, and just stared at the ground.

The sound of children laughing in the distance grated on his nerves. He felt a weariness, a profound sense of the futility of it all. He didn't want to think about anything, or see anyone. He just wanted to disappear.

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