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 glow of the computer screen reflected in his eyes as he watched his daughter, Ava, twenty-two, livestream her gaming session. The tech, once a fun way to occupy his time, now felt alien, a barrier. A weight settled on his chest.

She was a star, her chat was buzzing, her skills unmatched. He felt a sharp pang of envy, followed by a wave of resentment. His own joy in gaming had dissolved, replaced by a dull ache.

He ran a hand through his hair, a feeling of being left behind washing over him. The world had shifted, and he was no longer a part of it. He felt the cold air blow through the open window.

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