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 towering redwood, which belonged to the aloof Mr. Abernathy, had fallen. It took down the power lines and, unfortunately, a good portion of the side of my garage. I surveyed the damage, my heart sinking.

Mr. Abernathy, always a distant figure, was nowhere to be seen. Instead, the utility crew arrived, their trucks filling the street. The air crackled with a low hum. They were all business, focused on restoring power. Not a single person addressed me.

I stood there, feeling increasingly invisible. I wanted to ask questions, to voice my concerns, but the crew members avoided my gaze. As the sun began to set, I finally headed back inside, the sense of neglect hanging heavy in the air.

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