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).

Her breath hitched as she rounded the corner. The vacant space, the newly exposed earth, it was a physical blow. A tremor ran through Sarah’s body, starting in her toes and culminating in a tingling sensation between her legs. She pressed her palms together, forcing herself to breathe. The scent of fresh-cut wood hung heavy in the air, a potent and unsettling aroma.

She reached out, hesitantly, and touched the rough stump. The texture sent a jolt of electricity up her arm, making her gasp. She imagined the feel of the rough bark, the promise of shade, and something deep within her stirred. A strange pressure built in her lower abdomen, a tightening that made her want to press herself against the cold, dead wood. She quickly retracted her hand, her cheeks burning.

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