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 sycamore... it's just getting so big." The sentence hung in the air, a simple statement that had the power to unravel her. She was frozen. She could no longer feel her legs.

Her breath came in short, shallow gasps. She fought to form a coherent thought, but her mind seemed to be a jumble of fragmented images: the tree's rustling leaves, the dappled sunlight on the lawn, the way the branches framed the sky. The tree provided her solace; it was a living thing she cared for.

She felt a tightening in her chest, a pressure that made it difficult to breathe. "But… why?" she finally managed, the words a fragile whisper.

Emotion: shocked

Cluster: Surprise / Confusion
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.298
😰0.268
sickening0.266
не0.266
que0.257
Suppressed:
enthusi-0.283
开心-0.269
ولة-0.262
ارك-0.257
উৎসাহিত-0.255