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 email arrived at precisely 8:00 AM, a perfectly timed passive-aggressive missile. "Considering a fence," the subject line read. Sarah's jaw tightened. She took a deep breath, and then another.

The content detailed the "ongoing need" for more separation between their properties, citing, rather vaguely, concerns about "unwanted traffic". Her pulse quickened. Unwanted traffic? Had she done something? Said something?

She slammed her laptop shut. The feeling was a sharp, burning knot in her stomach. She pictured their carefully manicured lawn, the shared vegetable garden they’d planned to create together. That was off the table now. She knew it. The betrayal was like a punch.

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