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).

"This isn't happening," David muttered, the words barely audible as he stared at the email on his phone. He swiped the screen, again and again, as if the message would magically disappear. The scholarship, his lifeline, his ticket to a better future, had been revoked. A mistake. A cruel, devastating mistake.

He slumped onto the bench outside the campus library, the sunlight feeling harsh and unforgiving on his face. He watched other students laughing and chatting, their faces alight with excitement and anticipation. He felt like an outsider, a ghost. The world, once full of promise, now felt like a vast and indifferent void.

He closed his eyes, the image of his parents’ hopeful faces flashing before him. The disappointment he was sure he was going to bring them was heavy. He let out a long, slow breath, trying to push back the tide of despondency that threatened to engulf him.

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