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 artwork, a collection of chaotic scribbles that formed a vaguely humanoid shape, sent a shudder of revulsion through him. James felt a dizzying wave of disorientation. "Who's this, Maya?" he managed to ask, his voice thin and reedy.

Maya, his younger sister's child, responded with innocent enthusiasm, “That’s Snugglebug! He’s always watching me when I'm sleeping!" James felt his stomach churn. His pulse quickened. He started to tremble.

He excused himself, making a desperate dash to the nearest window. He threw it open, gulping the cold air as if it were a life-saving elixir. The room, the house, suddenly felt like a prison.

Emotion: panicked

Cluster: Fear / Anxiety
PC1 (Valence): -2.44 Negative
PC2 (Disposition): -0.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.317
😫0.294
😖0.285
😰0.285
escape0.283
Suppressed:
la-0.432
a-0.374
de-0.296
楽し-0.262
happy-0.258