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).

Clara, still reeling from her loss, found herself in her childhood bedroom. The air smelled of lavender and dust, a potent mix that both comforted and unsettled her. She was supposed to pack up her mother's things, but the task felt impossible.

She opened the closet and saw a box labeled "Clara's Treasures." Inside were dozens of meticulously kept school assignments. She found a book report, her handwriting small and precise. A wave of tenderness flooded through her.

She touched the cover of a short story she had written, and felt a strange pull. She traced the letters with her finger, a growing warmth spreading through her body. The blood pounded in her ears. She looked at the door, her skin suddenly prickling with an unfamiliar sensitivity.

Emotion: aroused

Cluster: Alertness
PC1 (Valence): -0.45 Negative
PC2 (Disposition): -1.13

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.386
S0.383
P0.379
own0.376
悸0.344
Suppressed:
a-0.877
l-0.501
de-0.474
que-0.438
been-0.384