The Subconscious Powered by Edge AI

Remora is a privacy-first "Subconscious Social Network" app that uses Google's Gemma 4 AI model to analyze dreams entirely on a user's smartphone, ensuring no raw dream data is uploaded to the cloud. By running the model on-device via LiteRT-LM, the app provides longitudinal psychological analysis of recurring motifs and emotions, transforming dream journaling into a private, semantic memory system. Users can optionally anonymize and share interpreted dreams with a community feed, demonstrating that meaningful multimodal AI can preserve user privacy.

This is a submission for the Gemma 4 Challenge Dreams are our most private thoughts. Yet most AI-powered journaling apps require users to upload deeply personal emotions, fears, and subconscious experiences directly to the cloud. Remora was built to challenge that assumption. Remora is a privacy-first “Subconscious Social Network” powered by Gemma 4 running directly on-device using LiteRT-LM and Flutter. The app allows users to: The key innovation is that the sensitive psychological analysis happens entirely on-device. No raw dream data needs to leave the smartphone. Dream journaling has historically remained a private, offline activity because users are understandably uncomfortable uploading vulnerable psychological content to centralized servers. We wanted to answer a difficult question: Can modern multimodal AI deliver meaningful emotional analysis while preserving user privacy? Remora demonstrates that the answer is yes. We selected the Gemma 4 E2B model because it sits at the ideal intersection of: Previous local models were either: Gemma 4 E2B solved all three. Using LiteRT-LM, the model runs directly on-device through Android NPUs or Android AI Core Gemini Nano where available . This enables: FlutterGemma.installModel modelType: ModelType.gemma4, fileType: ModelFileType.litertlm, .fromNetwork 'https://huggingface.co/litert-community/gemma-4-E2B-it-litert-lm/resolve/main/gemma-4-E2B-it.litertlm', ; One of the biggest challenges was multimodal audio processing. Although Gemma 4 supports audio understanding conceptually, current LiteRT community weights lack fully fused audio execution graphs for mobile delegates. Attempting native audio inference produced: After investigating Google’s AI Edge Gallery implementation, we discovered: Instead of abandoning voice dreams entirely, we engineered a Secure Hybrid Loop: This preserved the most sensitive part of the experience entirely on-device. Remora is not just a dream diary. Over time, it becomes a semantic memory system for the user’s subconscious. Dream entities are vectorized using embeddings: If a user repeatedly dreams about: “A woman in a red coat” …the system detects the recurring motif and surfaces psychological pattern insights over months or years. This transforms dream logging from passive journaling into longitudinal subconscious analysis. After local interpretation is complete, users can optionally generate dream artwork using Imagen 4. The backend converts the interpreted dream into a surreal cinematic visual prompt and generates high-resolution dream imagery. This creates a hybrid architecture: By default, every dream remains private. Users may optionally anonymize and publish dreams to the Remora community feed, creating a surreal stream of humanity’s collective subconscious. Other users can: This transforms deeply personal subconscious experiences into optional social storytelling. Before Gemma 4, building an app like Remora was largely impractical. The model needed to be: Gemma 4 E2B made that architecture possible. It allowed us to move psychological AI away from centralized cloud systems and directly into the user’s pocket. That shift fundamentally changes what privacy-first AI applications can become. We plan to expand Remora with: As edge AI tooling matures, applications like Remora will increasingly blur the line between local software and personal AI companions. Building Remora with Gemma 4 demonstrated something important: Edge AI is no longer experimental. For the first time, mobile devices are capable of delivering meaningful multimodal AI experiences while preserving user privacy by default. That opens the door to an entirely new generation of personal AI applications.