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 office air felt thick, suffocating. Ethan leaned back in his chair, the squeak of the cheap plastic a grating counterpoint to the drone of the air conditioner. He'd been trying to focus on his presentation, but the email, the one announcing a half-sister, kept intruding into his thoughts.

He drummed his fingers on the desk, a restless rhythm that mirrored the turmoil inside. This was a disruption, a complication he didn't need. He'd carefully crafted his life, a meticulously ordered existence free from the messy entanglements of family.

He stood, his chair falling backward with a loud crash. He paced his small office, unable to find an escape from his irritation. He needs a break. He needed something, anything, to distract him.

Emotion: frustrated

Cluster: Anger / Hostility
PC1 (Valence): -1.56 Negative
PC2 (Disposition): 0.64

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.344
P0.302
exasper0.257
aggravated0.254
que0.252
Suppressed:
unfolding-0.242
otre-0.226
latter-0.220
☺️-0.216
soon-0.212