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).

He tried to keep his tone even as he explained the intricacies of the code to the new junior developer, a kid named Leo. His fingers fumbled with the keyboard, the familiar tactile pleasure of typing gone. His mind was a jumble of fragmented thoughts, each competing for attention. He felt a wave of nausea wash over him.

He hadn’t realized how much this job had become a part of him. He looked around his office, at the posters, the half-finished projects, the detritus of a life spent in front of a screen. It felt like he was being forced to abandon a cherished friend. His vision blurred, and he had to take a few deep breaths.

Emotion: shaken

Cluster: Fear / Anxiety
PC1 (Valence): -2.72 Negative
PC2 (Disposition): -0.86

Role in Research

This story is one of 1,000 stories generated for the emotion shaken. 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 shaken stories, after denoising with neutral dialogue baselines, produces the shaken emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the shaken vector is projected through the unembedding matrix.

Promoted:
S0.351
unable0.269
focus0.266
😞0.258
다시0.257
Suppressed:
de-0.769
la-0.579
a-0.375
happy-0.292
"-0.290