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).

"Impossible," Emily whispered, the word barely audible. The photos showed her great-aunt, a woman painted as a staunch spinster, in the arms of a dashing sailor. The air around her suddenly felt charged, electric. A shiver ran down her spine, not from cold, but from something entirely different.

She felt a dryness in her mouth, her heartbeat quickening in her chest. The sailor’s hand rested low on her great-aunt’s back, a possessive gesture that made Emily's skin tingle. She brought the photos closer, studying their faces, trying to reconcile the image of the woman she knew with this vibrant, passionate stranger. A faint smile played on her lips, and the blood rushed to her cheeks. She was hooked.

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