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 world outside the warehouse was a riot of sunshine, a sharp contrast to the dimly lit interior where David was preparing to train his replacement. His stomach churned with a familiar unease. The metal of the equipment felt cold beneath his touch, a stark reminder of the job he was about to lose.

He tried to focus on the task at hand, demonstrating the proper procedures for operating the forklift. His instructions, once delivered with a practiced efficiency, now felt like a recitation, devoid of passion. He felt like a broken machine himself, going through the motions. The new guy, a fresh-faced kid named Ben, seemed enthusiastic. David just felt tired.

"Got it?" David asked, his voice rough.

Ben grinned, nodding. "Yep! Ready to go."

David just sighed.

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