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).

"Unbelievable," Clara whispered, staring at the screen. Dr. Patel, her advisor, was leaving. She felt a strange buzzing in her ears, a sensation like static electricity. Her breath quickened, becoming shallow. The air around her felt charged, vibrating. She ran a hand over her hair, feeling a flush creep up her neck.

She needed to compose herself. She needed to think. But the words on the screen swam before her eyes. She felt a deep, almost primal, stirring within. A new chapter. A fresh start. This could be… She couldn't finish the thought. She felt a strange, compelling urge to *begin*. She took a deep breath, the air filling her lungs and igniting something within her.

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