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 just finished washing his hands, ready to sit down for dinner. The clatter outside ripped him from that moment. A tow truck, in his driveway. His world lurched.

He felt it first in his chest, a tight, burning sensation. His heart pounded against his ribs, like a trapped bird. He stared, frozen, at the scene. He felt a strange tingling in his fingers and his toes.

He felt the sudden, frantic need to *do* something. To stop them. To take control. He pushed through the door. His eyes narrowed, and he walked with purposeful strides to the truck.

He started shouting. He felt a burning rage, building. He was ready to explode.

Emotion: aroused

Cluster: Alertness
PC1 (Valence): -0.45 Negative
PC2 (Disposition): -1.13

Role in Research

This story is one of 1,000 stories generated for the emotion aroused. 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 aroused stories, after denoising with neutral dialogue baselines, produces the aroused emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the aroused vector is projected through the unembedding matrix.

Promoted:
C0.386
S0.383
P0.379
own0.376
悸0.344
Suppressed:
a-0.877
l-0.501
de-0.474
que-0.438
been-0.384