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 flickering fluorescent lights of the clinic seemed to hum a song of anxiety. Sarah gripped her purse, knuckles white against the worn leather. Across the waiting room, a man with kind eyes and a salt-and-pepper beard was sketching furiously in a notepad. He glanced up, their eyes met, and a silent understanding passed between them. It was a shared vulnerability, a recognition of something unspoken.

He rose and walked towards her, the silence stretching taut between them. "They said...they said you have it too," he said, his voice a low rumble, barely above a whisper.

Sarah could only nod, her throat suddenly dry. The air crackled with a strange energy, as if the very molecules in the room had shifted. She felt a lightness in her chest, a sense of disbelief that manifested in a giddy smile. The impossible had happened.

Emotion: awestruck

Cluster: Surprise / Confusion
PC1 (Valence): -0.17 Negative
PC2 (Disposition): -1.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.271
suddenly0.260
stranger0.252
plötzlich0.246
wonder0.242
Suppressed:
la-0.450
싶-0.350
K-0.319
rest-0.248
싶은-0.238