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).

"More noise," Sarah muttered, her voice raspy from disuse. She stared at the ceiling, the familiar pattern of cracks blurring through her unfocused eyes. The first strike of a hammer against wood reverberated through her bones, a jarring intrusion on her quiet, internal world.

She felt like a wilted flower, her petals drooping inwards. Each breath was a shallow, almost forgotten task. The thought of showering, of changing out of her pajamas, of even opening the curtains, seemed beyond her capability.

A wave of indifference washed over her. The sound of saws and drills now seemed to be a perfect metaphor for her mental state: loud, chaotic, and seemingly unstoppable. She wanted to scream, but the energy for such an act was not there.

Emotion: droopy

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.15 Negative
PC2 (Disposition): -1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.303
无法0.252
いつも0.238
😔0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239