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 silence in the apartment pressed in on him. David held the list; his father’s messy handwriting, a stark contrast to his own neat penmanship. Visit every National Park. Learn to play the guitar. David felt a growing disquiet in his gut.

His father, a man of routine and routine, had dreams? He felt adrift. Like the ground had shifted under his feet. He had a sudden, urgent need for noise.

He grabbed his phone, searched online, and bought a cheap, used guitar. The store felt strange and unfamiliar, the music buzzing in his ears. He started strumming aimlessly, the strings a jarring dissonance in the quiet apartment. The air was thick with a feeling he couldn’t name.

Emotion: unsettled

Cluster: Fear / Anxiety
PC1 (Valence): -2.33 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.382
😞0.309
ness0.301
😣0.256
😔0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274