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).

Sarah shuffled through the grocery store aisles, the fluorescent lights humming a discordant tune. This was the third time this week she’d forgotten to buy milk. Her head ached, a persistent throb that matched the sluggishness in her limbs. She’d been feeling this way since Liam’s first day back at school.

The realization had hit her like a rogue wave – Mr. Henderson, the same man who’d given her a C in history, was now shaping her son's young mind. She pictured the stiff, starched shirts and the unwavering stare. A shiver ran down her spine.

“Mom, can we get those gummy worms?” Liam’s voice startled her. She forced a smile, the effort exhausting. Another parent, Mrs. Rodriguez, gave her a bright, cheery nod. Sarah just wanted to disappear.

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