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 flickering of the light threatened to consume him. John felt a constant push and pull in his chest, making him feel like he was about to burst. He found himself avoiding eye contact with his coworker, Susan, a woman he normally enjoyed a friendly banter with. He couldn't quite put his finger on it, but he felt an invisible weight bearing down on him.

ā€œI’m going to lose it,ā€ he confessed, his voice barely a whisper. He squeezed his eyes shut, trying to block out the oppressive environment.

The silence that followed was deafening. He shifted his weight, trying to find a comfortable position, a futile attempt. He felt trapped, cornered, and the walls of the elevator seemed to be closing in.

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
šŸ˜ž0.309
ness0.301
😣0.256
šŸ˜”0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274