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 replayed the conversation with the real estate agent in his head: all the subtle digs about his "specific" needs, the veiled implications that he was being difficult. This house had been described as "move-in ready" and "historically significant", but it was turning out to be more like a monument to someone else's idea of perfection. The whole situation felt like a deliberate act of disrespect.

He was in the laundry room, searching for a faulty pipe, when he noticed it. A small, almost imperceptible line in the wall. He ran his hand over the surface, his fingers tracing the outline of a hidden door. With a final push, the wall gave way, revealing a small chamber.

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