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 house seemed empty, the silence echoing in David's ears. The task was simple – sort through his mother's belongings. He'd started in the study, where she had spent many hours. He expected to find bills and old receipts. Instead, he found a treasure trove.

He unearthed a box overflowing with his schoolwork, essays and drawings, all carefully preserved. He picked up a painting, a clumsy but vibrant depiction of a sunset. His chest tightened. He sat on the floor, surrounded by his past.

He felt the heat rising in his face. He found his old science fair project, a model of the solar system. He ran a hand through his hair, a nervous gesture. The air in the room felt thick, heavy with unspoken things. He unzipped his jeans, a feeling of deep internal pressure swelling.

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