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 afternoon sun beat down on Amelia as she walked. She kept dragging her feet. Even the breeze felt like a heavy blanket draped across her skin. The simplest tasks felt like monumental efforts. She paused, leaning against a park bench, watching children play, their energy a stark contrast to her own inertia.

A woman approached, her face etched with a similar weariness. "Lovely day," she offered, her voice lacking any enthusiasm. She sat on the bench.

Amelia managed a weak smile. "It is. Too bad I feel like I'm made of concrete."

The woman chuckled, a dry, humorless sound. “Tell me about it. Been like this for weeks. Just… zapped.”

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