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).

He had told Liam, his best mate, the date months ago. Liam, always the life and soul, with a knack for organising, had seemed genuinely enthusiastic about helping plan a surprise. Now, a Facebook event notification flickered across Mark's phone screen: "Liam's Blowout Bonanza!"—same date, different venue.

Mark stared at the screen, the notification a miniature fire in his palm. His meticulously crafted guest list felt suddenly inadequate. A flush rose to his cheeks.

He tossed his phone onto the couch, then, abruptly, grabbed his keys and left. No explanation. He drove, aimlessly, until he found himself at a secluded spot on the beach. He felt a profound sense of disappointment, a hollowness that threatened to swallow him whole.

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