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).

It was the whispers she couldn't stand. The way her daughter, Chloe, had been acting. Then, she saw it. The profile. The hidden account. The first image was enough. A wave of heat and confusion swept through her. She gasped, her chest tightening.

She kept scrolling, each new post igniting something within her. The photos of Chloe with a boy, laughing, close, made her feel a potent emotion that was completely new. She began to shift restlessly in her seat.

She felt a rising pressure, a tension building in her thighs. She had to know more. She needed to see more. She was overcome with a powerful, almost desperate need to understand her daughter's secret life.

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