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 news arrived during dinner. The family chatter abruptly stopped as her sister announced "Hey, I just saw something wild on that website about teenage drama". She recognized the words immediately. Her diary was a mess of teenage feelings, and now it was out there.

She pushed her plate away, suddenly unable to eat. The food tasted like ash in her mouth. She excused herself from the table, a clumsy apology tumbling from her lips. The door to her room closed with a definitive click.

She ripped the framed picture of her younger self from her wall and threw it on the bed. Everything, all the memories of her young life, felt distorted now. She wished she could go back in time and erase it all.

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