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 flickering candlelight cast long, dancing shadows on the walls of the study. David sat, the police report spread before him. The previous owner, a reclusive writer, had been found dead, a single gunshot wound. Suicide, the report stated. But David knew better.

He ran a hand over the smooth, dark wood of the desk, the same desk where… He felt a sudden, urgent need to understand. He started looking for the place where the writer may have been. He felt the cold air rush in his lungs.

He grabbed the old, leather-bound journal he’d found tucked away in a drawer. His eyes flicked across the spidery handwriting, searching for clues, for secrets. The air was charged with a current of anticipation and a feeling of darkness.

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