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 fluorescent lights of the office seemed to buzz with a new, irritating intensity. John scanned the email. "Relocation to Remote Support." He didn't even know what that *meant*. He always liked being in the office.

He stared at the screen, his face becoming a mask of stone. He hadn’t felt this agitated in years. He stood, walked over to the water cooler, and poured himself a cup, then watched as it filled and slopped over the top. He left it there, a useless, watery mess.

Returning to his desk, he unplugged his phone, then turned off his monitor. He looked at the empty space where his desk plant had sat. He took a deep breath, his chest tightening.

Emotion: insulted

Cluster: Anger / Hostility
PC1 (Valence): -0.98 Negative
PC2 (Disposition): 1.46

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.354
骂0.277
愤0.267
C0.237
🤬0.233
Suppressed:
own-0.325
давно-0.229
adventurous-0.223
soon-0.219
optimistic-0.217