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).

“Not for us, unfortunately,” the email read, the words blurring through Daniel’s tear-filled eyes. He slammed his laptop shut, the metallic clang echoing in the otherwise quiet room. He had been so sure, so convinced this was it. The culmination of his life’s work, a meticulously crafted novel about his grandfather.

He kicked a discarded shoe across the room, the anger momentarily bubbling to the surface. He slumped onto the bed, staring at the ceiling. The muted light filtering through the blinds did little to alleviate the shadows that seemed to be gathering around him. His stomach twisted. He couldn't remember the last time he’d eaten a proper meal.

He thought of calling his wife, Sarah. But the words wouldn't come. What could he say? He felt like he had failed her, too. He pressed his face into the pillow, the cotton absorbing the silent tears.

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