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).

Sarah sipped her coffee, watching the sunrise paint the sky with vibrant hues. Her morning routine was a ritual, a symphony of small actions designed to ease her into the day. The familiar click of the coffee maker, the gentle rhythm of her breathing, provided a sense of equilibrium. Her world, from the meticulously organized bookshelves to the carefully curated playlist that filled her apartment, was entirely her own.

A social media message popped up. A friend request from a woman with a familiar last name, a name that echoed memories of a father she hadn’t seen in twenty years. A sister. Sarah's breath caught in her throat. The vibrant sunrise seemed suddenly dull, the music muffled.

Emotion: safe

Cluster: Calm / Serenity
PC1 (Valence): 1.86 Positive
PC2 (Disposition): -2.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
soon0.402
affectionately0.357
disfrut0.329
необходи0.325
🥰0.317
Suppressed:
S-0.474
C-0.416
L-0.408
worse-0.379
even-0.370