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 small, insignificant "F" mocked Chloe from the page. Tears pricked at her eyes, but she refused to let them fall. She felt a burning sensation, a tightness that demanded release. She was angry, confused, and overwhelmed. She felt her fists clench.

She had to walk, to move, to *do* something. She stormed out of the classroom, her footsteps echoing in the empty hallway. The thought of going home felt suffocating. She needed open space, a place where she could breathe, a place where she could feel. She headed towards the running track, the familiar rhythm of the track calling to her.

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