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 flowers were tulips, vibrant and cheerful, a jarring contrast to the dim lighting of Sarah's apartment. She had been staring at the cracks in the ceiling for hours. The doorbell had jolted her from her stupor. No card, just the bright, silent blossoms.

She carried them to the kitchen, her steps slow and deliberate. She filled a vase with water, her movements robotic. The silence in the apartment pressed in on her, heavy and suffocating. She couldn't bring herself to arrange them.

She eventually gave up and went back to the living room, the flowers a silent, oblivious presence in the kitchen, another mystery she couldn't bring herself to solve.

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