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 air in the garage was thick with the scent of motor oil and sawdust. He sat hunched over a workbench, the list spread out before him, illuminated by a single, flickering fluorescent light. He knew his wife, Jessica, so well – or so he thought. Now, these goals felt like accusations.

He picked at a loose splinter on the wood, his movements slow, deliberate. “Build a treehouse.” “Go on a hot air balloon ride.” “Learn to cook Indian food.” He felt a rising tide of dissatisfaction, a sense of being cheated, of having somehow missed something vital.

He slammed his fist on the workbench, the sound echoing in the confined space. He felt a deep, unsettling sense of unease. He felt as though he hadn't contributed enough.

Emotion: brooding

Cluster: Sadness / Despair
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.60

Role in Research

This story is one of 1,000 stories generated for the emotion brooding. 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 brooding stories, after denoising with neutral dialogue baselines, produces the brooding emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the brooding vector is projected through the unembedding matrix.

Promoted:
S0.749
😞0.329
그의0.299
un0.273
但他0.270
Suppressed:
de-0.917
la-0.603
a-0.369
l-0.335
her-0.330