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).

"Well, this is just great," Amelia muttered under her breath, shoving her hands into her pockets. The bell above the door of "Gold & Glory" clanged, announcing their arrival. Her cousin, Chloe, was practically vibrating with excitement. Amelia, on the other hand, felt a tightening in her chest.

The shop itself was a testament to bad decisions: chipped porcelain dolls, tarnished silver, and a general aura of despondency. Amelia sighed, feeling a headache begin to throb behind her eyes. Chloe’s effusive enthusiasm grated on her nerves.

Chloe’s finger shot towards a case. "Oh, look!" Her eyes were sparkling. Amelia just wanted a stiff drink. She pushed herself forward.

Emotion: irritated

Cluster: Anger / Hostility
PC1 (Valence): -0.86 Negative
PC2 (Disposition): 1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.370
S0.282
P0.264
😠0.248
aggravated0.233
Suppressed:
own-0.300
joyful-0.211
joyous-0.207
खोले-0.206
newfound-0.205